There's so much hype and bullshit around Machine Learning (ML). And if I have to read one more crappy prediction of who survived on the Titantic, I'll go postal.

So, what real-world problems are you using it to address...and how successful has it been? What decisions have you supported using ML? What models did you use (e.g. logistic regression, decision trees, ANN)?

Anyone got any boringly useful examples of ML in production?

And don't say you're using it to predict survival rates for the design of new cruise ships...although, to be fair, that might be quite interesting...

I'm not an expert in machine learning, can only tell from management perspective.

Most successful and boring were improvements in text and pattern matching.

E.g. an decade old (not joking… seriously 12 year plus) order system from which we extracted company / buyer data.

As one can imagine there were several small deviations per address, e.g. an additional C/O, a typo in the address, ...

We created via ML a hashed tree of companies - the ML part aggregated the companies / addresses and their deviations, primary keys to keep the relational database association.

Much better statistics - and deduplication of data.

Indeed

Unpopular opinion here, Data Scientists are just failed statistician. Most of them don't even understand the most basic principles the whole domain relies upon

@Yggdrasil I think a lot of “data science” is currently being done by people who learned python and imported sklearn.

But yes...statistics. What’s the science in “data science” if it’s not stats (with some linear algebra and calculus throw in)?

Interesting

@platypus I whole heartedly agree with your point on python. Ease of access is a great thing and all but it does not remove the necessity to understand the problem domain.